Machine learning search for variable stars

Abstract

Photometric variability detection is often considered as a hypothesis testing problem: an object is variable if the null-hypothesis that its brightness is constant can be ruled out given the measurements and their uncertainties. Uncorrected systematic errors limit the practical applicability of this approach to high-amplitude variability and well-behaving data sets. Searching for a new variability detection technique that would be applicable to a wide range of variability types while being robust to outliers and underestimated measurement uncertainties, we propose to consider variability detection as a classification problem that can be approached with machine learning. We compare several classification algorithms: Logistic Regression (LR), Support Vector Machines (SVM), k-Nearest Neighbors (kNN) Neural Nets (NN), Random Forests (RF) and Stochastic Gradient Boosting classifier (SGB) applied to 18 features (variability indices) quantifying scatter and/or correlation between points in a light curve. We use a subset of OGLE-II Large Magellanic Cloud (LMC) photometry (30265 light curves) that was searched for variability using traditional methods (168 known variable objects identified) as the training set and then apply the NN to a new test set of 31798 OGLE-II LMC light curves. Among 205 candidates selected in the test set, 178 are real variables, 13 low-amplitude variables are new discoveries. We find that the considered machine learning classifiers are more efficient (they find more variables and less false candidates) compared to traditional techniques that consider individual variability indices or their linear combination. The NN, SGB, SVM and RF show a higher efficiency compared to LR and kNN.

19 pages, 13 figures, 5 tables; accepted to MNRAS

References in corpus (62)

• Scikit-learn: Machine Learning in Python
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• The VizieR database of Astronomical Catalogues
• A method for optimal image subtraction
• First Results from the Catalina Real-time Transient Survey
• The PLATO 2.0 Mission
• The All-Sky Automated Survey for Supernovae (ASAS-SN) Light Curve Server v1.0
• The Palomar Transient Factory: System Overview, Performance and First Results
• The Dark Energy Survey: more than dark energy - an overview
• VISTA Variables in the Via Lactea (VVV): The public ESO near-IR variability survey of the Milky Way
• The MACHO Project: Microlensing Results from 5.7 Years of LMC Observations
• A box-fitting algorithm in the search for periodic transits
• Limits on the Macho Content of the Galactic Halo from the EROS-2 Survey of the Magellanic Clouds
• The CoRoT satellite in flight : description and performance
• Wide-field millimagnitude photometry with HAT: A Tool for Extra-solar Planet Detection
• Northern Sky Variability Survey (NSVS): Public data release
• The Kilodegree Extremely Little Telescope (KELT): A Small Robotic Telescope for Large-Area Synoptic Surveys
• The first WASP public data release
• The VMC Survey - I. Strategy and First Data
• CHEOPS: A Transit Photometry Mission for ESA's Small Mission Programme
• Distributed and parallel time series feature extraction for industrial big data applications
• BRITE-Constellation: nanosatellites for precision photometry of bright stars
• Exploring the Variable Sky with LINEAR. III. Classification of Periodic Light Curves
• Photometric Variability in Kepler Target Stars. III. Comparison with the Sun on Different Timescales
• Testing tests on AGN microvariability
• Global stellar variability study in the field-of-view of the Kepler satellite
• Red variables in the OGLE-II database. I. Pulsations and period-luminosity relations below the tip of the Red Giant Branch of the LMC
• Comparative performance of selected variability detection techniques in photometric time series
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• Are solar brightness variations faculae- or spot-dominated?
• A Package for the Automated Classification of Periodic Variable Stars
• The OGLE View of Microlensing towards the Magellanic Clouds. I. A Trickle of Events in the OGLE-II LMC data
• The BRITE Constellation nanosatellite mission: Testing, commissioning and operations
• The Properties of Long-Period Variables in the Large Magellanic Cloud from MACHO
• The Multi-site All-Sky CAmeRA: Finding transiting exoplanets around bright ($m_V<8$) stars
• Statistics of Stellar Variability from Kepler - I: Revisiting Quarter 1 with an Astrophysically Robust Systematics Correction
• Automated analysis of eclipsing binary lightcurves. I. EBAS -- a new Eclipsing Binary Automated Solver with EBOP
• The Magellanic Quasars Survey. III. Spectroscopic Confirmation of 758 AGNs Behind the Magellanic Clouds
• Periodic and Aperoidic Variability in the Molecular Cloud ρOphiuchus
• BRITE-Constellation: Data processing and photometry
• A machine learned classifier for RR Lyrae in the VVV survey
• Detecting Variability in Massive Astronomical Time-Series Data I: application of an infinite Gaussian mixture model
• Data augmentation for machine learning redshifts applied to SDSS galaxies
• Improved Photometry for the DASCH Pipeline
• Emission-line stars discovered in the UKST H-alpha survey of the Large Magellanic Cloud; Part 1: Hot stars
• Variable stars in the globular cluster NGC 7492. New discoveries and physical parameters determination
• A Refined QSO Selection Method Using Diagnostics Tests: 663 QSO Candidates in the LMC
• Long Period Variables in the Large Magellanic Cloud from the EROS-2 survey
• Astrokit -- an Efficient Program for High-Precision Differential CCD Photometry and Search for Variable Stars
• New Insights into Time Series Analysis - I - Correlated observations
• Precision multi-band photometry with a DSLR camera
• Searching transients in large-scale surveys. A method based on the Abbe value
• First results of the Kourovka Planet Search: discovery of transiting exoplanet candidates in the first three target fields
• Improved Variable Star Search in Large Photometric Data Sets -- New Variables in CoRoT Field LRa02 Detected by BEST II
• Photometric detection of high proper motions in dense stellar fields using Difference Image Analysis
• Gaia Data Release 1: The variability processing & analysis and its application to the south ecliptic pole region
• Color and Variability Characteristics of Point Sources in the Faint Sky Variability Survey
• Variable classification in the LSST era: Exploring a model for quasi-periodic light curves
• Machine learning techniques to select Be star candidates. An application in the OGLE-IV Gaia south ecliptic pole field
• Difference image analysis: Automatic kernel design using information criteria
• Detecting Variability in Massive Astronomical Time-Series Data II: Variable Candidates in the Northern Sky Variability Survey
• A sample of GHz-peaked spectrum sources selected at RATAN-600: spectral and variability properties

Cited by in corpus (34)

• The ASAS-SN Catalog of Variable Stars I: The Serendipitous Survey
• Machine Learning for the Zwicky Transient Facility
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Identification of Young Stellar Object candidates in the $Gaia$ DR2 x AllWISE catalogue with machine learning methods
• Atmospheric circulation of brown dwarfs and directly imaged exoplanets driven by cloud radiative feedback: effects of rotation
• Catalogue of new Herbig Ae/Be and classical Be stars. A machine learning approach to Gaia DR2
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Star formation rates and stellar masses from machine learning
• Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
• Imbalance Learning for Variable Star Classification
• The ZTF Source Classification Project: I. Methods and Infrastructure
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• AutoRegressive Planet Search: Methodology
• The ZTF Source Classification Project: II. Periodicity and variability processing metrics
• A Machine Learning Classifier for Microlensing in Wide-Field Surveys
• Variable star classification across the Galactic bulge and disc with the VISTA Variables in the Vía Láctea survey
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• A machine-learning photometric classifier for massive stars in nearby galaxies I. The method
• Machine Learning Classification of Gaia Data Release 2
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Flares hunting in hot subdwarf and white dwarf stars from Cycles 1-5 of TESS photometry
• Protostellar classification using supervised machine learning algorithms
• Understanding of the properties of neural network approaches for transient light curve approximations
• The Hubble Catalog of Variables (HCV)
• Variable Star Classification Using Multi-View Metric Learning
• Long-Period High-Amplitude Red Variables in the KELT Survey
• A Fast Approximate Approach to Microlensing Survey Analysis
• Automatic Catalog of RRLyrae from $\sim$ 14 million VVV Light Curves: How far can we go with traditional machine-learning?
• Variability search in M 31 using Principal Component Analysis and the Hubble Source Catalog
• Classifying High-cadence Microlensing Light Curves I; Defining Features
• Searching for Quasi-Periodic Eruptions using Machine Learning
• Construction of a far ultraviolet all sky map from an incomplete survey: Application of a deep learning algorithm
• Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
• Advanced Astroinformatics for Variable Star Classification